Discovering signature of electronic social networks

1. A computer system, comprising:

a processor;

a memory; and

a program comprising a plurality of instructions stored in the memory that are executed by the processor to:

identify one user's connections with other users in an electronic social network;

create a data structure in the memory that represents the one user, the other users, and the one user's connections with the other users;

analyze a plurality of data sources for electronic communications between the one user and the other users;

assign a relative importance value to each data source of the plurality of data sources;

assign a weight to each connection between the one user and the other users, the weight being an encoded value computed based on a link structure of the connections, the link structure including metadata indicating a category and a status of the respective connections, the weight enabling an emulation and behavioral prediction of the electronic social network in response to a stimulus applied to the electronic social network;

weight electronic communications data from each data source of the plurality of data sources based on the assigned relative importance value of each data source;

calculate for each of the other users the probability that the one user will communicate with that other user based on the analyzed plurality of data sources and the weight values;

rank the one user's connections with the other users based on the calculated probabilities;

remove from the data structure one or more data structure elements of the one user's connections based on the ranked one user's connections to create a signature graph; and

form a diagnostic model of the electronic social network, the diagnostic model including the signature graph to accelerate a processing speed of the diagnostic model on a social network analysis system.

2. The computer system of claim 1 , wherein the plurality of instructions further comprises instructions that are executed by the processor to calculate for each of the other users the probability that the one user will communicate with that other user based on the weighted electronic communications data from each data source.

3. The computer system of claim 1 , wherein the plurality of instructions further comprises instructions that are executed by the processor to remove from the graph one or more of the one user's connections that are ranked lower than a predetermined threshold ranking.

4. The computer system of claim 1 , wherein the plurality of instructions further comprises instructions that are executed by the processor to apply a ranking rule to the signature graph.

5. The computer system of claim 4 , wherein the plurality of instructions further comprises instructions that are executed by the processor to generate a rank matrix based on the application of the ranking rule.

6. A computer program product for ranking one user's connections in an electronic social network, the computer program product comprising:

at least one non-transitory computer readable medium having computer readable program instructions embodied therewith, the computer readable program instructions, when read by a processor, being configured to:

identify one user's connections with other users in an electronic social network;

create a data structure in the memory that represents the one user, the other users, and the one user's connections with the other users;

analyze a plurality of data sources for electronic communications between the one user and the other users;

assign a relative importance value to each data source of the plurality of data sources;

assign a weight to each connection between the one user and the other users, the weight being an encoded value computed based on a link structure of the connections, the link structure including metadata indicating a category and a status of the respective connections, the weight enabling an emulation and behavioral prediction of the electronic social network in response to a stimulus applied to the electronic social network;

weight electronic communications data from each data source of the plurality of data sources based on the assigned relative importance value of each data source;

calculate for each of the other users the probability that the one user will communicate with that other user based on the analyzed plurality of data sources and the weight values;

rank the one user's connections with the other users based on the calculated probabilities;

remove from the data structure one or more data structure elements of the one user's connections based on the ranked one user's connections to create a signature graph; and

form a diagnostic model of the electronic social network, the diagnostic model including the signature graph to accelerate a processing speed of the diagnostic model on a social network analysis system.

7. The computer program product of claim 6 , wherein the instructions further comprises instructions configured to calculate for each of the other users the probability that the one user will communicate with that other user based on the weighted electronic communications data from each data source.

8. The computer program product of claim 6 , wherein the instructions further comprises instructions configured to remove from the graph one or more of the one user's connections that are ranked lower than a predetermined threshold ranking.

9. The computer program product of claim 6 , wherein the instructions further comprises instructions configured to apply a ranking rule to the signature graph.

10. The computer program product of claim 9 , wherein the instructions further comprises instructions configured to generate a rank matrix based on the application of the ranking rule.